Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    step by step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ^{*}}{\
    0.47
    ,\"
    0.41
    )}}{\
    0.41
    袠
    0.40
    📦
    0.40
    \",
    0.39
    */)
    0.38
    .\"
    0.38
    }$.)
    0.37
    坴
    0.37
    POSITIVE LOGITS
    ikoa
    0.44
    ′
    0.43
     ’
    0.41
     (’
    0.37
    \'
    0.36
     hyped
    0.36
    ichero
    0.36
     stripper
    0.36
    uki
    0.36
    ிலான
    0.36
    Act Density 0.001%

    No Known Activations